Massi Michela Carlotta, Gasperoni Francesca, Ieva Francesca, Paganoni Anna Maria, Zunino Paolo, Manzoni Andrea, Franco Nicola Rares, Veldeman Liv, Ost Piet, Fonteyne Valérie, Talbot Christopher J, Rattay Tim, Webb Adam, Symonds Paul R, Johnson Kerstie, Lambrecht Maarten, Haustermans Karin, De Meerleer Gert, de Ruysscher Dirk, Vanneste Ben, Van Limbergen Evert, Choudhury Ananya, Elliott Rebecca M, Sperk Elena, Herskind Carsten, Veldwijk Marlon R, Avuzzi Barbara, Giandini Tommaso, Valdagni Riccardo, Cicchetti Alessandro, Azria David, Jacquet Marie-Pierre Farcy, Rosenstein Barry S, Stock Richard G, Collado Kayla, Vega Ana, Aguado-Barrera Miguel Elías, Calvo Patricia, Dunning Alison M, Fachal Laura, Kerns Sarah L, Payne Debbie, Chang-Claude Jenny, Seibold Petra, West Catharine M L, Rancati Tiziana
Modelling and Scientific Computing Laboratory, Math Department, Politecnico di Milano, Milan, Italy.
Center for Analysis, Decisions and Society, Human Technopole, Milan, Italy.
Front Oncol. 2020 Oct 15;10:541281. doi: 10.3389/fonc.2020.541281. eCollection 2020.
REQUITE (validating pREdictive models and biomarkers of radiotherapy toxicity to reduce side effects and improve QUalITy of lifE in cancer survivors) is an international prospective cohort study. The purpose of this project was to analyse a cohort of patients recruited into REQUITE using a deep learning algorithm to identify patient-specific features associated with the development of toxicity, and test the approach by attempting to validate previously published genetic risk factors. The study involved REQUITE prostate cancer patients treated with external beam radiotherapy who had complete 2-year follow-up. We used five separate late toxicity endpoints: ≥grade 1 late rectal bleeding, ≥grade 2 urinary frequency, ≥grade 1 haematuria, ≥ grade 2 nocturia, ≥ grade 1 decreased urinary stream. Forty-three single nucleotide polymorphisms (SNPs) already reported in the literature to be associated with the toxicity endpoints were included in the analysis. No SNP had been studied before in the REQUITE cohort. Deep Sparse AutoEncoders (DSAE) were trained to recognize features (SNPs) identifying patients with no toxicity and tested on a different independent mixed population including patients without and with toxicity. One thousand, four hundred and one patients were included, and toxicity rates were: rectal bleeding 11.7%, urinary frequency 4%, haematuria 5.5%, nocturia 7.8%, decreased urinary stream 17.1%. Twenty-four of the 43 SNPs that were associated with the toxicity endpoints were validated as identifying patients with toxicity. Twenty of the 24 SNPs were associated with the same toxicity endpoint as reported in the literature: 9 SNPs for urinary symptoms and 11 SNPs for overall toxicity. The other 4 SNPs were associated with a different endpoint. Deep learning algorithms can validate SNPs associated with toxicity after radiotherapy for prostate cancer. The method should be studied further to identify polygenic SNP risk signatures for radiotherapy toxicity. The signatures could then be included in integrated normal tissue complication probability models and tested for their ability to personalize radiotherapy treatment planning.
REQUITE（验证放疗毒性的预测模型和生物标志物以减少副作用并提高癌症幸存者的生活质量）是一项国际前瞻性队列研究。该项目的目的是使用深度学习算法分析纳入REQUITE的一组患者，以识别与毒性发生相关的患者特异性特征，并通过尝试验证先前发表的遗传风险因素来测试该方法。该研究涉及接受外照射放疗且有完整2年随访的REQUITE前列腺癌患者。我们使用了五个不同的晚期毒性终点：≥1级晚期直肠出血、≥2级尿频、≥1级血尿、≥2级夜尿、≥1级尿流减少。分析中纳入了43个先前文献报道与毒性终点相关的单核苷酸多态性（SNP）。REQUITE队列中此前未对任何SNP进行过研究。训练深度稀疏自动编码器（DSAE）以识别可区分无毒性患者的特征（SNP），并在包括有毒性和无毒患者的不同独立混合人群中进行测试。共纳入1401例患者，毒性发生率分别为：直肠出血11.7%、尿频4%、血尿5.5%、夜尿7.8%、尿流减少17.1%。与毒性终点相关的43个SNP中有24个被验证可识别有毒性的患者。这24个SNP中有20个与文献报道的相同毒性终点相关：9个SNP与泌尿系统症状相关，11个SNP与总体毒性相关。另外4个SNP与不同的终点相关。深度学习算法可验证前列腺癌放疗后与毒性相关的SNP。应进一步研究该方法以识别放疗毒性的多基因SNP风险特征。然后可将这些特征纳入综合正常组织并发症概率模型，并测试其个性化放疗治疗计划的能力。
